DJMeng
> 晚点会有 期待您更新权重文件，可以测试看看，谢谢
So far, you can export onnx on pyotrch 1.3, opset 10, tensorrt7.0, and you should fixed model input size,like this : if the model input 1,3,192,512: ( function forward() in...
> > Such as：mobilenet-v2, I trained 40 epochs,The loss dropped very slowly, only from 30 to 25. > > I Tried on EfficientNet-B4, loss also dropped so so so slow....
do you solve it? thank you very much.
Did you solve it?
> Did you solve it? pip uninstall yapf pip install yapf it is ok！
please
同问， 是基于train data的链接里 自己拼的语料嘛？谢谢
> > [@KohakuBlueleaf](https://github.com/KohakuBlueleaf) any chance you can help here? I tried moving tensors to both devices but couldn't resolve the problem > > My next update for resolution bucket will...